Extracting Information from Encrypted Data using Deep Neural Networks

Extracting Information from Encrypted Data using Deep Neural Networks

In this paper we explore various approaches to using deep neural networks to per- form cryptanalysis, with the ultimate goal of having a deep neural network deci- pher encrypted data. We use long short-term memory networks to try to decipher encrypted text and we use a convolutional neural network t...

Full description

Bibliographic Details
Main Author: Lagerhjelm, Linus
Format: Others
Language:English
Published: Umeå universitet, Institutionen för tillämpad fysik och elektronik 2018
Subjects:
Neuralnetworks
MachineLearning
Cryptography
DES
LSTM
CNN
Cryptanalysis
Media and Communication Technology
Medieteknik
Online Access:http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-155904
id ndltd-UPSALLA1-oai-DiVA.org-umu-155904
record_format oai_dc
spelling ndltd-UPSALLA1-oai-DiVA.org-umu-1559042019-02-05T08:41:10ZExtracting Information from Encrypted Data using Deep Neural NetworksengLagerhjelm, LinusUmeå universitet, Institutionen för tillämpad fysik och elektronik2018NeuralnetworksMachineLearningCryptographyDESLSTMCNNCryptanalysisMedia and Communication TechnologyMedieteknikIn this paper we explore various approaches to using deep neural networks to per- form cryptanalysis, with the ultimate goal of having a deep neural network deci- pher encrypted data. We use long short-term memory networks to try to decipher encrypted text and we use a convolutional neural network to perform classification tasks on encrypted MNIST images. We find that although the network is unable to decipher encrypted data, it is able to perform classification on encrypted data. We also find that the networks performance is depending on what key were used to en- crypt the data. These findings could be valuable for further research into the topic of cryptanalysis using deep neural networks. Student thesisinfo:eu-repo/semantics/bachelorThesistexthttp://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-155904application/pdfinfo:eu-repo/semantics/openAccess
collection NDLTD
language English
format Others
sources NDLTD
topic Neuralnetworks
MachineLearning
Cryptography
DES
LSTM
CNN
Cryptanalysis
Media and Communication Technology
Medieteknik
spellingShingle Neuralnetworks
MachineLearning
Cryptography
DES
LSTM
CNN
Cryptanalysis
Media and Communication Technology
Medieteknik
Lagerhjelm, Linus
Extracting Information from Encrypted Data using Deep Neural Networks
description In this paper we explore various approaches to using deep neural networks to per- form cryptanalysis, with the ultimate goal of having a deep neural network deci- pher encrypted data. We use long short-term memory networks to try to decipher encrypted text and we use a convolutional neural network to perform classification tasks on encrypted MNIST images. We find that although the network is unable to decipher encrypted data, it is able to perform classification on encrypted data. We also find that the networks performance is depending on what key were used to en- crypt the data. These findings could be valuable for further research into the topic of cryptanalysis using deep neural networks.
author Lagerhjelm, Linus
author_facet Lagerhjelm, Linus
author_sort Lagerhjelm, Linus
title Extracting Information from Encrypted Data using Deep Neural Networks
title_short Extracting Information from Encrypted Data using Deep Neural Networks
title_full Extracting Information from Encrypted Data using Deep Neural Networks
title_fullStr Extracting Information from Encrypted Data using Deep Neural Networks
title_full_unstemmed Extracting Information from Encrypted Data using Deep Neural Networks
title_sort extracting information from encrypted data using deep neural networks
publisher Umeå universitet, Institutionen för tillämpad fysik och elektronik
publishDate 2018
url http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-155904
work_keys_str_mv AT lagerhjelmlinus extractinginformationfromencrypteddatausingdeepneuralnetworks
_version_ 1718974085836308480

Similar Items